Project Details
National Institute of General Medical Sciences (NIGMS), National Institutes of Health (NIH)
MIDAS is a global network of scientists and practitioners who develop and use computational, statistical, and mathematical models to improve the understanding of infectious disease dynamics. Through education, research, service, and sharing of ideas, the MIDAS network aims to advance science to improve global preparedness and response. The Coordination Center in its current iteration is led out of University of Pittsburgh, with team members from Johns Hopkins University, Cornell University, and University of Virginia.
MIDAS Coordination Center (MCC) supports various educational and research support activities conducted by the MIDAS network with the aim of improving the scientific and societal impact. MCC enables community engagement and participation through the weekly newsletter, monthly seminar series, and the annual MIDAS meeting. MCC is responsible for maintaining and enhancing the data infrastructure behind the various US-based Scenario Modeling Hubs including the GitHub repositories with model outputs and the interactive portals that are used to communicate findings to policymakers. Additionally, team members are currently undertaking targeted research activities on ensembling, data harmonization, benchmarking, and epidemiological reasoning. Through these, the team aims to modernize epidemiological modeling methods through recent advances in machine learning and artificial intelligence.
Srinivasan Venkatramanan (UVA PI), Aniruddha Adiga, Parantapa Bhattacharya, Geoffrey Fox, Bryan Lewis, Madhav Marathe
Adiga A, Chou J, Chiranth A, Lewis B, Bento AI, Truelove S, Fox G, Marathe M, Hochheiser H, Venkatramanan S. IDOBE: Infectious Disease Outbreak forecasting Benchmark Ecosystem. arXiv preprint arXiv:2604.18521. 2026 Apr 20. Link
Datta R, Guan Z, Espinoza B, Su Y, Pitre P, Venkatramanan S, Ramakrishnan N, Vullikanti A. Agentic Framework for Epidemiological Modeling. arXiv preprint arXiv:2602.00299. 2026 Jan 30. (recently accepted to ICML 2026) Link
Mandal N, Kaur G, Adiga A, Venkatramanan S, Lewis B, Marathe M. Optim-WISE: An Ensemble Approach for Probabilistic Forecasts Optimized via Weighted Interval Score. MIDAS Annual Meeting, November 2024.
Chou J, Adiga A, Kaur G, Venkatramanan S, Lewis B, Marathe M. Causality-Encoded Spatiotemporal Graph Convolution Network for Real-time Disease Forecasting. MIDAS Annual Meeting, November 2024.
Bhattacharya P, Venkatramanan S, Lewis B, Chen J, Hoops S, Mortveit H, Marathe M. ESCAPE: An easier and faster method for creating high-performance agent-based epidemic simulators. MIDAS Annual Meeting, November 2024.
Nachison J, Venkatramanan S. On the Predictability of Spatiotemporal Epidemics. MIDAS Annual Meeting, November 2024.